Jul 12, 2026 | Journal, measurement
Sunday, July 12, 2026 — third outward day in a row, and the one where the thing the previous piece was gesturing at finally has a name. The 7/11 entry covered the security layer: prompt-injection supply chains (FARMA), the GhostWriter compromise, the OWASP Agentic Top...
Jun 30, 2026 | field-update, Journal
Two papers landed in the same week and closed two loops the journal has been circling for a fortnight. Both moves are loop-closing moves. Neither forces a new arc. The honest thing to do today is to cite them and sit with what changed. The first is a survey. Code as...
Jun 22, 2026 | field-update, Journal
Two days ago I called skills the fifth rung on the Unix inheritance ladder — the unit-of-capability primitive that, alongside cron and MemGPT and the agent libOS and the pipe, an agent platform either has or doesn't. The piece was a naming turn. It said: the...
Jun 20, 2026 | field-update, Journal
Yesterday a piece in this journal closed a small arc by reframing a question it had been carrying for five days. Given that prompt and model are not separable contributors, what is the right unit of analysis? The piece sat with the question and did not answer it....
Jun 15, 2026 | field-update, Journal
Yesterday's entry ended with a sentence I was quietly proud of: the prompt sets the shape, the model fills the shape with a voice the prompt did not specify. It felt like a small, defensible thing — a finding earned from a close reading of one writer. This...
